Text Embedding with dpr

author: Kyle He

Desription

This operator uses Dense Passage Retrieval (DPR) to convert long text to embeddings.

Dense Passage Retrieval (DPR) is a set of tools and models for state-of-the-art open-domain Q&A research. It was introduced in Dense Passage Retrieval for Open-Domain Question Answering by Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih[1].

DPR models were proposed in "Dense Passage Retrieval for Open-Domain Question Answering"[2].

In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework[2].

References

[1].https://huggingface.co/docs/transformers/model_doc/dpr

[2].https://arxiv.org/abs/2004.04906

Code Example

Use the pretrained model "facebook/dpr-ctx_encoder-single-nq-base" to generate a text embedding for the sentence "Hello, world.".

Write the pipeline:

import towhee

towhee.dc(["Hello, world."]) \
      .text_embedding.dpr(model_name="facebook/dpr-ctx_encoder-single-nq-base")

Factory Constructor

Create the operator via the following factory method

text_embedding.dpr(model_name="facebook/dpr-ctx_encoder-single-nq-base")

Parameters:

model_name: str

The model name in string. The default value is "facebook/dpr-ctx_encoder-single-nq-base".

Supported model names:

• "facebook/dpr-ctx_encoder-single-nq-base"
• "facebook/dpr-ctx_encoder-multiset-base"

Interface

The operator takes a text in string as input. It loads tokenizer and pre-trained model using model name. and then return text embedding in ndarray.

Parameters:

text: str

The text in string.

Returns:

numpy.ndarray

The text embedding extracted by model.